A regression framework to head-circumference delineation from US fetal images. (January 2021)

• Record Type: Journal Article
• Authors: Fiorentino, Maria Chiara; Moccia, Sara; Capparuccini, Morris; Giamberini, Sara; Frontoni, Emanuele
• Is Part Of: Computer methods and programs in biomedicine. Volume 198(2021)
• Publication Date: 2021-01
• Subjects: Fetal ultrasounds -- Head circumference delineation -- Regression networks -- Convolutional neural networks; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105771
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Head-circumference (HC) has an important role in the evaluation of fetal growth. We propose an automatic algorithm to directly delineate HC in US images. The approach is based on a regression CNN trained with distance field. A mean absolute difference = 1.9 mm was obtained testing the HC18 Challenge dataset. Abstract: Background and Objectives: Measuring head-circumference (HC) length from ultrasound (US) images is a crucial clinical task to assess fetus growth. To lower intra- and inter-operator variability in HC length measuring, several computer-assisted solutions have been proposed in the years. Recently, a large number of deep-learning approaches is addressing the problem of HC delineation through the segmentation of the whole fetal head via convolutional neural networks (CNNs). Since the task is a edge-delineation problem, we propose a different strategy based on regression CNNs. Methods: The proposed framework consists of a region-proposal CNN for head localization and centering, and a regression CNN for accurately delineate the HC. The first CNN is trained exploiting transfer learning, while we propose a training strategy for the regression CNN based on distance fields. Results: The framework was tested on the HC18 Challenge dataset, which consists of 999 training and 335 testing images. A mean absolute difference of 1.90 ( ± 1.76) mm and a Dice similarity coefficient of 97.75 ( ± 1.32) % were achieved, overcoming approaches in the literature. Conclusions: The experimental results showed the effectiveness of the proposed framework, proving its potential in supporting clinicians during the clinical practice.